From d8b02cc359724b68daeb21f0d8b6dfb6c6453312 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E8=8B=8F=E9=9D=A9=E5=B2=9A?= <13190755+sugotland@user.noreply.gitee.com> Date: Thu, 13 Jul 2023 03:33:53 +0000 Subject: [PATCH] =?UTF-8?q?=E4=B8=8A=E4=BC=A0=E9=A2=84=E5=A4=84=E7=90=86?= =?UTF-8?q?=E6=96=87=E4=BB=B6?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: 苏革岚 <13190755+sugotland@user.noreply.gitee.com> --- .../数据预处理、相关性及可视化分析.ipynb | 1046 +++++++++++++++++ 1 file changed, 1046 insertions(+) create mode 100644 共享单车数据分析/数据预处理、相关性及可视化分析.ipynb diff --git a/共享单车数据分析/数据预处理、相关性及可视化分析.ipynb b/共享单车数据分析/数据预处理、相关性及可视化分析.ipynb new file mode 100644 index 0000000..361fd2d --- /dev/null +++ b/共享单车数据分析/数据预处理、相关性及可视化分析.ipynb @@ -0,0 +1,1046 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "import matplotlib.pyplot as plt\n", + "import seaborn as sns\n", + "from sklearn.model_selection import train_test_split\n", + "import plotly.express as px\n", + "from sklearn.metrics import mean_squared_log_error, r2_score\n", + "from sklearn.linear_model import LinearRegression, Ridge\n", + "from sklearn.preprocessing import StandardScaler\n", + "from sklearn.decomposition import PCA\n", + "from sklearn.ensemble import AdaBoostRegressor\n", + "from sklearn.ensemble import RandomForestRegressor, GradientBoostingRegressor\n", + "from sklearn.svm import SVR\n", + "from datetime import datetime\n", + "\n", + "# 设置中文支持\n", + "plt.rcParams['font.sans-serif'] = ['SimHei']\n", + "plt.rcParams['axes.unicode_minus'] = False" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# 导入数据" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "train_df = pd.read_csv('train.csv')\n", + "test_df = pd.read_csv('test.csv')" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "train_df" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "train_df.info()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "test_df.info()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "得：无整行重复,无缺失值NAN，但可以评估列中某些值为零的数据（例如风速），以确认 0 是否为缺失值。" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# 合并训练集和测试集" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "print(type(train_df))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "#full = train_df.append(test_df, ignore_index=True)\n", + "full=pd.concat([train_df,test_df],ignore_index=True)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "full.info()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# 拆分时间变量\n", + "full['date'] = full.datetime.apply(lambda c: c.split()[0])\n", + "full['hour'] = full.datetime.apply(lambda c: c.split()[1].split(':')[0]).astype('int')\n", + "full['year'] = full.datetime.apply(lambda c: c.split()[0].split('-')[0]).astype('int')\n", + "full['month'] = full.datetime.apply(lambda c: c.split()[0].split('-')[1]).astype('int')\n", + "\n", + "\n", + "def get_weekday(x):\n", + " date1 = x.split()[0]\n", + " date2 = datetime.strptime(date1, '%Y-%m-%d')\n", + " week_day = date2.weekday()\n", + " return week_day\n", + "\n", + "full['weekday'] = full.datetime.apply(get_weekday)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "full.head()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# 异常值处理" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "fig, axes = plt.subplots(nrows=3,ncols=2)\n", + "fig.set_size_inches(15, 20)\n", + "sns.boxplot(data=full,y=\"count\",orient=\"v\",ax=axes[0][0])\n", + "sns.boxplot(data=full,y=\"count\",x=\"hour\",orient=\"v\",ax=axes[0][1])\n", + "sns.boxplot(data=full,y=\"count\",x=\"season\",orient=\"v\",ax=axes[1][0])\n", + "sns.boxplot(data=full,y=\"count\",x=\"workingday\",orient=\"v\",ax=axes[1][1])\n", + "sns.boxplot(data=full,y=\"count\",x=\"holiday\",orient=\"v\",ax=axes[2][0])\n", + "sns.boxplot(data=full,y=\"count\",x=\"weather\",orient=\"v\",ax=axes[2][1])\n", + "\n", + "axes[0][0].set(ylabel='Count',title=\"Count\")\n", + "axes[0][1].set(xlabel='Hour Of The Day', ylabel='Count',title=\"Count by Hour of the Day\")\n", + "axes[1][0].set(xlabel='Season', ylabel='Count',title=\"Count by Season\")\n", + "axes[1][1].set(xlabel='Working Day', ylabel='Count',title=\"Count by Working Day\")\n", + "axes[2][0].set(xlabel='Holiday', ylabel='Count',title=\"Count by Holiday\")\n", + "axes[2][1].set(xlabel='Weather', ylabel='Count',title=\"Count by Weather\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "季节对比显示，春季的自行车租赁量较低。\n", + "具有均值信息的方框图是一天中的时间段，因为它显示最繁忙的时间段是早上7点到8点和下午5点到6点，这意味着用户主要租用自行车去上班/上学和下班回家。\n", + "根据方框图4和5（工作日和节假日），我们发现大多数异常值都出现在工作日。从节假日来看，结果是合理的，因为所有异常值都出现在非节假日。\n", + "最后一个方框图显示了一个显而易见的常识，即大多数用户在天气晴朗和多云时租用自行车（1和2），而在大雨或下雪时几乎没有用户租用自行车（3）。" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "使用3σ规则来剔除异常值。如果有一个数据点落在平均值的三个标准差之外，则该数据点被视为离群点，可以从数据集中删除。这种方法假定数据呈正态分布，离群值为罕见事件，将来不太可能出现。" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# Function to detect and print outliers\n", + "def detect_outliers(data):\n", + " # mean, standard deviation and 3-sigma of the data\n", + " mean = np.mean(data)\n", + " std = np.std(data)\n", + " threesigma = 3 * std\n", + "\n", + " # print upper, lower boundary and boxplot\n", + " sns.boxplot(data, orient=\"v\")\n", + " plt.show()\n", + " lower, upper = mean-3*std, mean+3*std\n", + " print(f\"Upper and lower boundary is: {lower}/{upper}\")\n", + "\n", + " # identify outliers and return the outliers\n", + " outliers = [x for x in data if np.abs(x - mean) > threesigma]\n", + " print(f\"There are {len(outliers)} outliers based on three-sigma rule\")\n", + "\n", + "# Function to delete the outliers\n", + "def delete_outliers(data, df):\n", + " # detecting and dropping outliers\n", + " original_shape = df.shape\n", + " mean = np.mean(data)\n", + " std = np.std(data)\n", + " outliers = np.abs(data-mean) > (3*std)\n", + " outliers_num = len(train_df[outliers])\n", + " df.drop(index=data[outliers].index, inplace=True)\n", + "\n", + " # print what was deleted\n", + " print(\"Number of outliers deleted:\", outliers_num)\n", + " print (\"Shape of dataframe with Ouliers: \",original_shape)\n", + " print (\"Shape of Dataframe After Deleting the Ouliers: \",df.shape)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "train_with_outliers = train_df\n", + "# 查找异常值\n", + "detect_outliers(train_df['count'])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# 从训练集删除异常值\n", + "delete_outliers(train_df['count'], train_df)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "对于大多数机器学习技术来说，因变量的正态性假设并不总是必要或可取的。虽然一些传统的统计模型假设因变量的正态性，但许多机器学习算法（如决策树、随机森林和神经网络）并不依赖于此假设。\n", + "\n", + "但是，请务必注意，当输入特征或预测变量近似呈正态分布时，某些算法可能会假设或表现更好。如果因变量表现出极端偏度或异常值，则应用变换或使用对非正态性更稳健的替代模型可能是有益的" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## temp 温度" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "print(f\"偏度为：{train_df['temp'].skew()}\")\n", + "full['temp'].describe()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "sns.distplot(full['temp'])" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## atemp 体感温度" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "print(f\"偏度为：{train_df['atemp'].skew()}\")\n", + "full['atemp'].describe()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "sns.distplot(full['atemp'])" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## windspeed 风速" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "sns.distplot(full['windspeed'])\n", + "a = full[full['windspeed'] == 0].shape[0]\n", + "print(f'风速为0的天数为：{a}')\n", + "print(f\"偏度为：{train_df['windspeed'].skew()}\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "风速为0天数过多，可能存在异常。" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "## 处理缺失值\n", + "windspeed_df1 = full[full['windspeed'] != 0]\n", + "windspeed_df2 = full[full['windspeed'] == 0]\n", + "windspeed_df2['windspeed'] = windspeed_df1['windspeed'].interpolate()\n", + "#full = windspeed_df1.append(windspeed_df1)\n", + "full = pd.concat([windspeed_df1,windspeed_df2])\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "sns.distplot(full['windspeed'])\n", + "a = full[full['windspeed'] == 0].shape[0]\n", + "print(f'风速为0的天数为：{a}')" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "full.info()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Humidity 湿度" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "print(f\"偏度为：{train_df['humidity'].skew()}\")\n", + "train_df['humidity'].describe()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "sns.distplot(full['humidity'])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "train_df[train_df['humidity'] == 0].shape[0]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "湿度值为0和100为异常数据，考虑可能有传感器错误情况。" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# 各个变量与租车数量的关系" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "sns.pairplot(full, x_vars=['holiday', 'workingday', 'weather', 'season', 'windspeed', 'humidity', 'temp', 'atemp'],\n", + " y_vars=['casual', 'registered', 'count'], plot_kws={'alpha': 0.1})" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# 相关性分析" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "full.corr()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "plt.figure(figsize=(13, 10))\n", + "sns.heatmap(full.corr(), annot=True, cmap='YlOrBr_r')\n", + "plt.title('Heatmap on Correlation', fontsize=20)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# 租赁数量与其他变量的相关性\n", + "full.corr()['count'].sort_values(ascending=False)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "full.corr()['registered'].sort_values(ascending=False)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "full.corr()['casual'].sort_values(ascending=False)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# 可视化分类数据分析" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## temp 温度" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# 按温度取租赁数量平均值\n", + "tempr = full.groupby(['temp'], as_index=True).agg({'casual': 'mean', 'registered': 'mean', 'count': 'mean'})\n", + "tempr.plot(title='每小时平均租赁数量随温度变化的趋势',figsize=(7,3))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## atemp体感温度" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "atempr = full.groupby(['atemp'], as_index=True).agg({'casual': 'mean',\n", + " 'registered': 'mean',\n", + " 'count': 'mean'})\n", + "atempr.plot(title='每小时平均租赁数量随体感温度变化的趋势',figsize=(7,3))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# 湿度对租赁数量影响" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "humidityr = full.groupby(['humidity'], as_index=True).agg({'casual': 'mean',\n", + " 'registered': 'mean',\n", + " 'count': 'mean'})\n", + "\n", + "humidityr.plot(title='不同湿度下每小时的平均租赁次数',figsize=(7,3))\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 年份、月份对租赁数量的影响" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "day_df=full.groupby('date').agg({'year':'mean','month':'mean',\n", + " 'casual':'sum', 'registered':'sum'\n", + " ,'count':'sum'})\n", + "month_df = day_df.groupby(['year','month'], as_index=True).agg({'casual':'mean',\n", + " 'registered':'mean', 'count':'mean'})\n", + "month_df.plot(fontsize=8,figsize=(15,4))\n", + "tick=list(range(24))\n", + "labels=['2011.1','2011.2','2011.3','2011.4','2011.5','2011.6','2011.7','2011.8','2011.9','2011.10','2011.11','2011.12','2012.1','2012.2','2012.3','2012.4','2012.5','2012.6','2012.7','2012.8','2012.9','2012.10','2012.11','2012.12']\n", + "plt.xticks(tick,labels,fontsize=8)\n", + "plt.title('两年内每月租赁数量变化趋势', fontsize=15)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# 按天\n", + "day_df1=full.groupby('date').agg({\n", + " 'casual':'sum', 'registered':'sum'\n", + " ,'count':'sum'})\n", + "day_df1.plot(fontsize=8,figsize=(8,4),linewidth=0.8)\n", + "plt.title('两年内每天租赁数量变化趋势', fontsize=15 )" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "plt.figure(figsize=(15,4))\n", + "# 按年\n", + "plt.subplot(1,3,1)\n", + "sns.barplot(x=full['year'],y=full['count'])\n", + "plt.title('by year')\n", + "\n", + "# 按季度\n", + "plt.subplot(1,3,2)\n", + "sns.barplot(x=full['season'],y=full['count'])\n", + "plt.title('by season')\n", + "\n", + "# 按月\n", + "plt.subplot(1,3,3)\n", + "sns.barplot(x=full['month'],y=full['count'])\n", + "plt.title('by month')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 时段对租赁数量的影响" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "\n", + "fig,(ax1,ax2,ax3)= plt.subplots(nrows=3)\n", + "fig.set_size_inches(15,20)\n", + "full = full.reset_index(drop=True)\n", + "\n", + "sns.pointplot(x=full['hour'],y=full['count'],hue=full['season'],join=True, palette=\"Paired\", ax=ax1)\n", + "\n", + "sns.pointplot(x=full['hour'],y=full['count'],hue=full['weekday'],join=True, palette=\"Paired\", ax=ax2)\n", + "\n", + "sns.lineplot(x=full['hour'], y=full['registered'], color='red',label='Registered', marker='o', ax=ax3, ci=None)\n", + "sns.lineplot(x=full['hour'], y=full['casual'], color='blue', label='Casual', marker='o', ax=ax3, ci=None)\n", + "\n", + "ax3.set_ylabel('Count')\n", + "\n", + "ax1.set(xlabel='Hour of the Day', ylabel='Count',title=\"不同季节一天内每小时共享单车租借次数\")\n", + "ax2.set(xlabel='Hour of the Day', ylabel='Count',title=\"一天内每小时共享单车内租借次数\")\n", + "ax3.set(xlabel='Hour of the Day', ylabel='Count',title=\"一天内会员 vs 非会员每小时共享单车租借次数\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "COUNT与REGISTERED类似，但由于大多数用户是注册用户，他们的繁忙时间在上午7-8点和下午4-5点之间，而临时用户的繁忙时间在白天分布较好，但最繁忙的时间在下午1-2点之间。\n", + "下图显示了为什么春季是租赁量较少的季节。在所有季节中，春季是大雨/大雪天数最多的季节，这直接影响了租赁需求的减少。\n", + "下图中的 \"按季节分时段统计 \"显示了白天的租赁分布情况，这也证明了前面所说的春季是最不喜欢租车的季节。\n", + "秋季和夏季往往是租车人数最多的季节。\n", + "平日按时间段划分的图表显示，周六和周日的租车模式与平日明显不同，大多数用户在上午11点至下午4点租车。这些周末用户租车是为了休闲，而不是为了上班（上午8点和下午6点）。\n", + "在最后一张图中，\"注册用户数与休闲用户数 \"的休闲线中，周末用户的形态也很相似。这可能表明，注册用户是在工作日使用自行车的人，而临时用户在周末租车，在工作日租车时，不需要作为上班的交通工具。" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 天气对租赁情况影响" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "weather_count = full.groupby('weather')\n", + "weather_count[['casual', 'registered', 'count']].count()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "weather_df = full.groupby('weather', as_index=True).agg({'casual': 'mean', 'registered': 'mean', 'count': 'mean'})\n", + "weather_df.plot.bar(stacked=True, title='不同天气下每小时的平均租赁数量', color=['#c63d40', '#dc8f75', '#ffddb7'])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "weather_df.plot(figsize=(8,4))\n", + "plt.title('租借数量随天气变化的趋势')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 风速对租借情况影响" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# 考虑到风速特别大的时候很少，如果取平均值会出现异常，所以按风速对租赁数量取最大值。\n", + "windspeedr = full.groupby(['windspeed'], as_index=True).agg({'casual': 'max', 'registered': 'max', 'count': 'max'})\n", + "windspeedr.plot(title='不同风速下每小时启动的最大租赁数量',figsize=(8,4))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# 可以看到租赁数量随风速越大租赁数量越少，在风速超过30的时候明显减少，打印异常数据分析\n", + "df2 = full[full['windspeed'] > 40]\n", + "df2 = df2[df2['count'] > 400]\n", + "df2" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "因为是下班高峰期的时间" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 工作日与非工作日的租赁情况" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "day_df=full.groupby('date').agg({'year':'mean','season':'mean',\n", + " 'casual':'sum', 'registered':'sum'\n", + " ,'count':'sum','temp':'mean',\n", + " 'atemp':'mean','workingday':'mean'})\n", + "day_df" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# 对工作日和非工作日租赁数量取了平均值，对一周中每天的租赁数量求和\n", + "workingday_df = day_df.groupby(['workingday'], as_index=True).agg({'casual': 'mean', 'registered': 'mean'})\n", + "workingday_df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "workingday_df1 = workingday_df.loc[0]\n", + "workingday_df2 = workingday_df.loc[1]\n", + "workingday_df1.head()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# 绘制非工作日与工作日的临时借车数量和会员借车数量堆积图\n", + "width = 0.3\n", + "p1 = plt.bar(workingday_df.index, workingday_df['casual'], width,color='#dc8f75')\n", + "p2 = plt.bar(workingday_df.index, workingday_df['registered'], width, bottom=workingday_df['casual'],color='#ffddb7')\n", + "plt.title('工作日、非工作日每天平均租赁数量')\n", + "plt.xticks([0, 1], ('non-working day', 'working day'))\n", + "plt.legend((p1[0], p2[0]), ('casual', 'registered'))\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# 绘制非工作日临时借车数量和会员借车数量占比饼图\n", + "plt.subplot2grid((2, 2), (0, 0))\n", + "plt.pie(workingday_df1, labels=['casual', 'registered'], autopct='%1.1f%%',\n", + " pctdistance=0.6, labeldistance=1.35, radius=1.3,colors=['#c63d40','#ffddb7'])\n", + "plt.axis('equal')\n", + "plt.title('non-working day')\n", + "\n", + "# 绘制工作日临时借车数量和会员借车数量占比饼图\n", + "plt.subplot2grid((2, 2), (0, 1))\n", + "plt.pie(workingday_df2, labels=['casual', 'registered'], autopct='%1.1f%%',\n", + " pctdistance=0.6, labeldistance=1.35, radius=1.3,colors=['#c63d40','#ffddb7'])\n", + "plt.title('working day')\n", + "plt.axis('equal')" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "\n", + "# 查看工作日与非工作日每小时的临时租赁数量，会员租赁数量和总数量的平均值\n", + "workingday_df=full[full['workingday']==1]\n", + "workingday_df = workingday_df.groupby(['hour'], as_index=True).agg({'casual':'mean',\n", + " 'registered':'mean',\n", + " 'count':'mean'})\n", + "\n", + "nworkingday_df=full[full['workingday']==0]\n", + "nworkingday_df = nworkingday_df.groupby(['hour'], as_index=True).agg({'casual':'mean',\n", + " 'registered':'mean',\n", + " 'count':'mean'})\n", + "fig, axes = plt.subplots(1, 2,sharey = True)\n", + "\n", + "workingday_df.plot(figsize=(15,5),title = '工作日一天内租借数量变化趋势',ax=axes[0])\n", + "nworkingday_df.plot(figsize=(15,5),title = '非工作日一天内租借数量变化趋势',ax=axes[1])\n", + "\n", + "plt.show()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 节假日的租赁情况" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "day_df=full.groupby('date').agg({'year':'mean',\n", + " 'casual':'sum', 'registered':'sum'\n", + " ,'count':'sum','holiday':'mean'})\n", + "holiday_count=day_df.groupby('year', as_index=True).agg({'holiday':'sum'})\n", + "holiday_count" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "holiday_df = day_df.groupby('holiday', as_index=True).agg({'casual':'mean', 'registered':'mean'})\n", + "holiday_df.plot.bar(stacked=True , title = '假期或非假期每天的平均租赁数量',cmap='Set3')\n", + "plt.xticks(rotation=360)\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 会员与非会员" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "number_pei=day_df[['casual','registered']].mean()\n", + "number_pei" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "plt.axes(aspect='equal')\n", + "plt.pie(number_pei, labels=['casual','registered'], autopct='%1.1f%%',\n", + " pctdistance=0.6 , labeldistance=1.05 , radius=1 ,colors=['#c63d40','#ffddb7'])\n", + "\n", + "plt.title('会员与非会员租借数量占比')\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 决策树模型" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "from sklearn.tree import DecisionTreeClassifier\n", + "clf1 = DecisionTreeClassifier()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "train_df" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "train_features = train_df.iloc[:,1:-3]\n", + "train_labels_casual = train_df.iloc[:,-3]\n", + "test_features = test_df.iloc[:,1:]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "clf1.fit(train_features, train_labels_casual)\n", + "predicted_labels_casual = clf1.predict(test_features)\n", + "test_df['casual'] = predicted_labels_casual\n", + "test_df" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "clf2 = DecisionTreeClassifier()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "train_labels_registered = train_df.iloc[:,-2]\n", + "clf2.fit(train_features, train_labels_registered)\n", + "predicted_labels_registered = clf2.predict(test_features)\n", + "test_df['registered'] = predicted_labels_registered\n", + "test_df" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "test_df['count'] = test_df['casual'] + test_df['registered']" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "test_df" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "注：在决策树模型中，多次对同一数据进行机器学习，最终预测结果可能会有所不同。" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.11.1" + } + }, + "nbformat": 4, + "nbformat_minor": 1 +}